Python爬取的数据存为json文件,并读取

836次阅读
没有评论

Python爬取的数据存为json文件,并读取

import requests import time from lxml import etree import json

def json_data_save(url): headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36' }

html = requests.get(url,headers = headers).content.decode('gbk') data = etree.HTML(html) lists = data.xpath('//ul[@class="bigimg"]/li') dicts = {} names = [] athors = [] publishs = [] publish_times = [] prices = [] for lis in lists:

name = lis.xpath('./a/@title')[0] names.append(name) athor = lis.xpath('./p[@class="search_book_author"]/span/a/@title')[0] athors.append(athor) publish = lis.xpath('./p[@class="search_book_author"]/span/a/@title')[-1] publishs.append(publish) publish_time = lis.xpath('./p[@class="search_book_author"]/span/text()')[-2].split('/')[-1] publish_times.append(publish_time) price = lis.xpath('./p[@class="price"]/span[@class="search_now_price"]/text()')[0].split('¥')[-1] prices.append(price)

dicts['name'] = names dicts['athor'] = athors dicts['publish'] = publishs dicts['publish_time'] = publish_times dicts['price'] = prices # 保存数据为json格式 try: with open('a.json','a',encoding="utf-8") as f: f.write(json.dumps(dicts,ensure_ascii=False)) #ensure_ascii=False,则返回值可以包含非ascii值 except IOError as e: print(str(e))

finally: f.close()

def open_json(path): try: with open(path,'r',encoding='utf-8') as f: js_data = json.load(f) print('这是json数据:',js_data) print('这是数据类型:', type(js_data)) except Exception as e: print(str(e)) finally: f.close()

if __name__ == '__main__': url = 'http://search.dangdang.com/?key=%D0%A1%CD%F5%D7%D3&act=input&page_index=1' json_data_save(url) time.sleep(1) path = 'a.json' open_json(path)

Python爬取的数据存为json文件,并读取

 

神龙|纯净稳定代理IP免费测试>>>>>>>>天启|企业级代理IP免费测试>>>>>>>>IPIPGO|全球住宅代理IP免费测试

相关文章:

版权声明:Python教程2022-10-27发表,共计1801字。
新手QQ群:570568346,欢迎进群讨论 Python51学习